diffix / explorer

Tool to automatically explore and generate stats on data anonymized using Diffix
MIT License
2 stars 1 forks source link

TextLengthComponent returns duplicate buckets #282

Closed dandanlen closed 4 years ago

dandanlen commented 4 years ago

Example from StackOverflowDevSurvey dataset:

text.length.values:[
  {
    "count": 6,
    "value": 4
  },
  {
    "count": 10,
    "value": 4
  },
  {
    "count": 507,
    "value": 4
  },
  {
    "count": 5,
    "value": 4
  },
  {
    "count": 66,
    "value": 4
  },
  {
    "count": 33,
    "value": 4
  },
  {
    "count": 250,
    "value": 5
  },
  {
    "count": 11,
    "value": 5
  },
  {
    "count": 125,
    "value": 5
  },
  {
    "count": 110,
    "value": 5
  },
  {
    "count": 46,
    "value": 5
  },
  {
    "count": 782,
    "value": 5
  },
  {
    "count": 240,
    "value": 5
  },
  {
    "count": 133,
    "value": 5
  },
  {
    "count": 10,
    "value": 5
  },
  {
    "count": 54,
    "value": 5
  },
  {
    "count": 2,
    "value": 5
  },
  {
    "count": 98,
    "value": 5
  },
  {
    "count": 15,
    "value": 5
  },
  {
    "count": 5196,
    "value": 5
  },
  {
    "count": 867,
    "value": 5
  },
  {
    "count": 42,
    "value": 6
  },
  {
    "count": 609,
    "value": 6
  },
  {
    "count": 1738,
    "value": 6
  },
  {
    "count": 779,
    "value": 6
  },
  {
    "count": 229,
    "value": 6
  },
  {
    "count": 28,
    "value": 6
  },
  {
    "count": 98,
    "value": 6
  },
  {
    "count": 363,
    "value": 6
  },
  {
    "count": 2235,
    "value": 6
  },
  {
    "count": 1289,
    "value": 6
  },
  {
    "count": 28,
    "value": 6
  },
  {
    "count": 299,
    "value": 6
  },
  {
    "count": 13,
    "value": 6
  },
  {
    "count": 352,
    "value": 6
  },
  {
    "count": 261,
    "value": 6
  },
  {
    "count": 13,
    "value": 6
  },
  {
    "count": 4,
    "value": 6
  },
  {
    "count": 11,
    "value": 6
  },
  {
    "count": 89,
    "value": 6
  },
  {
    "count": 575,
    "value": 6
  },
  {
    "count": 22,
    "value": 6
  },
  {
    "count": 6,
    "value": 6
  },
  {
    "count": 23,
    "value": 7
  },
  {
    "count": 564,
    "value": 7
  },
  {
    "count": 55,
    "value": 7
  },
  {
    "count": 77,
    "value": 7
  },
  {
    "count": 36,
    "value": 7
  },
  {
    "count": 286,
    "value": 7
  },
  {
    "count": 4141,
    "value": 7
  },
  {
    "count": 3,
    "value": 7
  },
  {
    "count": 42,
    "value": 7
  },
  {
    "count": 31,
    "value": 7
  },
  {
    "count": 172,
    "value": 7
  },
  {
    "count": 90,
    "value": 7
  },
  {
    "count": 402,
    "value": 7
  },
  {
    "count": 2,
    "value": 7
  },
  {
    "count": 332,
    "value": 7
  },
  {
    "count": 51,
    "value": 7
  },
  {
    "count": 77,
    "value": 7
  },
  {
    "count": 91,
    "value": 7
  },
  {
    "count": 122,
    "value": 7
  },
  {
    "count": 20,
    "value": 7
  },
  {
    "count": 6,
    "value": 7
  },
  {
    "count": 48,
    "value": 7
  },
  {
    "count": 37,
    "value": 7
  },
  {
    "count": 5,
    "value": 7
  },
  {
    "count": 12,
    "value": 7
  },
  {
    "count": 302,
    "value": 7
  },
  {
    "count": 479,
    "value": 7
  },
  {
    "count": 61,
    "value": 7
  },
  {
    "count": 344,
    "value": 7
  },
  {
    "count": 357,
    "value": 7
  },
  {
    "count": 174,
    "value": 7
  },
  {
    "count": 53,
    "value": 7
  },
  {
    "count": 17,
    "value": 8
  },
  {
    "count": 304,
    "value": 8
  },
  {
    "count": 14,
    "value": 8
  },
  {
    "count": 457,
    "value": 8
  },
  {
    "count": 271,
    "value": 8
  },
  {
    "count": 37,
    "value": 8
  },
  {
    "count": 150,
    "value": 8
  },
  {
    "count": 23,
    "value": 8
  },
  {
    "count": 19,
    "value": 8
  },
  {
    "count": 21,
    "value": 8
  },
  {
    "count": 260,
    "value": 8
  },
  {
    "count": 11,
    "value": 8
  },
  {
    "count": 68,
    "value": 8
  },
  {
    "count": 21,
    "value": 8
  },
  {
    "count": 192,
    "value": 8
  },
  {
    "count": 2,
    "value": 8
  },
  {
    "count": 121,
    "value": 8
  },
  {
    "count": 6,
    "value": 8
  },
  {
    "count": 123,
    "value": 9
  },
  {
    "count": 255,
    "value": 9
  },
  {
    "count": 177,
    "value": 9
  },
  {
    "count": 169,
    "value": 9
  },
  {
    "count": 60,
    "value": 9
  },
  {
    "count": 911,
    "value": 9
  },
  {
    "count": 54,
    "value": 9
  },
  {
    "count": 289,
    "value": 9
  },
  {
    "count": 39,
    "value": 9
  },
  {
    "count": 16,
    "value": 9
  },
  {
    "count": 14,
    "value": 9
  },
  {
    "count": 175,
    "value": 9
  },
  {
    "count": 31,
    "value": 10
  },
  {
    "count": 54,
    "value": 10
  },
  {
    "count": 11,
    "value": 10
  },
  {
    "count": 10,
    "value": 10
  },
  {
    "count": 27,
    "value": 10
  },
  {
    "count": 8,
    "value": 10
  },
  {
    "count": 183,
    "value": 10
  },
  {
    "count": 13,
    "value": 10
  },
  {
    "count": 34,
    "value": 10
  },
  {
    "count": 9,
    "value": 10
  },
  {
    "count": 19,
    "value": 11
  },
  {
    "count": 327,
    "value": 11
  },
  {
    "count": 7,
    "value": 11
  },
  {
    "count": 27,
    "value": 11
  },
  {
    "count": 165,
    "value": 11
  },
  {
    "count": 19,
    "value": 11
  },
  {
    "count": 252,
    "value": 11
  },
  {
    "count": 63,
    "value": 11
  },
  {
    "count": 598,
    "value": 11
  },
  {
    "count": 854,
    "value": 11
  },
  {
    "count": 52,
    "value": 12
  },
  {
    "count": 376,
    "value": 12
  },
  {
    "count": 11456,
    "value": 13
  },
  {
    "count": 23,
    "value": 13
  },
  {
    "count": 4,
    "value": 13
  },
  {
    "count": 4396,
    "value": 14
  },
  {
    "count": 6,
    "value": 14
  },
  {
    "count": 409,
    "value": 14
  },
  {
    "count": 170,
    "value": 15
  },
  {
    "count": 5,
    "value": 16
  },
  {
    "count": 9,
    "value": 17
  },
  {
    "count": 65,
    "value": 18
  },
  {
    "count": 875,
    "value": 18
  },
  {
    "count": 64,
    "value": 18
  },
  {
    "count": 139,
    "value": 19
  },
  {
    "count": 15,
    "value": 19
  },
  {
    "count": 5,
    "value": 20
  },
  {
    "count": 98,
    "value": 20
  },
  {
    "count": 9,
    "value": 22
  },
  {
    "count": 2,
    "value": 27
  },
  {
    "count": 2,
    "value": 27
  }